Skip to content

test(openai): Stop directly calling _calculate_*_token_usage() #7875

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
alexander-alderman-webb merged 8 commits into from
Oct 6, 2026
Merged

test(openai): Stop directly calling _calculate_*_token_usage() #7875

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a810175
test(openai): Stop directly calling _calculate_completions_token_usage()
alexander-alderman-webb Oct 6, 2026
2c7ae65
Use nonstreaming_responses_model_response fixture
alexander-alderman-webb Oct 6, 2026
b4f3688
add types
alexander-alderman-webb Oct 6, 2026
3139530
fix model input
alexander-alderman-webb Oct 6, 2026
7a440e4
parametrize tomkens in streaming fixture
alexander-alderman-webb Oct 6, 2026
2d16b1a
.
alexander-alderman-webb Oct 6, 2026
584e80d
preserve existing response chunks
alexander-alderman-webb Oct 6, 2026
f80a3b6
.
alexander-alderman-webb Oct 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
225 changes: 83 additions & 142 deletions tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1317,116 +1317,61 @@ def inner(request_headers=None):

@pytest.fixture
def streaming_chat_completions_model_response():
return [
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
role="assistant"
),
finish_reason=None,
),
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content="Tes"
),
finish_reason=None,
),
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content="t r"
),
finish_reason=None,
),
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content="esp"
),
finish_reason=None,
),
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content="ons"
def inner(
usage: "openai.types.CompletionUsage",
message_contents: "Iterator[str]",
):
return [
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
role="assistant"
),
finish_reason=None,
),
finish_reason=None,
),
],
),
*[
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content=message_content
),
finish_reason=None,
),
],
)
for message_content in message_contents
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(
content="e"
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(),
finish_reason="stop",
),
finish_reason=None,
),
],
),
openai.types.chat.ChatCompletionChunk(
id="chatcmpl-test",
object="chat.completion.chunk",
created=10000000,
model="gpt-3.5-turbo",
choices=[
openai.types.chat.chat_completion_chunk.Choice(
index=0,
delta=openai.types.chat.chat_completion_chunk.ChoiceDelta(),
finish_reason="stop",
),
],
usage=openai.types.CompletionUsage(
prompt_tokens=10,
completion_tokens=20,
total_tokens=30,
],
usage=usage,
),
),
]
]

return inner


@pytest.fixture
Expand Down Expand Up @@ -1479,42 +1424,38 @@ def openai_embedding_model_response():

@pytest.fixture
def nonstreaming_responses_model_response():
return openai.types.responses.Response(
id="resp_123",
output=[
openai.types.responses.ResponseOutputMessage(
id="msg_123",
type="message",
status="completed",
content=[
openai.types.responses.ResponseOutputText(
text="Hello, how can I help you?",
type="output_text",
annotations=[],
)
],
role="assistant",
)
],
parallel_tool_calls=False,
tool_choice="none",
tools=[],
created_at=10000000,
model="gpt-4",
object="response",
usage=openai.types.responses.ResponseUsage(
input_tokens=10,
input_tokens_details=openai.types.responses.response_usage.InputTokensDetails(
cached_tokens=4,
cache_write_tokens=6,
),
output_tokens=20,
output_tokens_details=openai.types.responses.response_usage.OutputTokensDetails(
reasoning_tokens=5,
),
total_tokens=30,
),
)
def inner(
message_contents: "Iterator[str]",
usage: "openai.types.responses.ResponseUsage",
):
return openai.types.responses.Response(
id="resp_123",
output=[
openai.types.responses.ResponseOutputMessage(
id="msg_123",
type="message",
status="completed",
content=[
openai.types.responses.ResponseOutputText(
text=message_content,
type="output_text",
annotations=[],
)
],
role="assistant",
)
for message_content in message_contents
],
parallel_tool_calls=False,
tool_choice="none",
tools=[],
created_at=10000000,
model="gpt-4",
object="response",
usage=usage,
)

return inner


@pytest.fixture
Expand Down
16 changes: 15 additions & 1 deletion tests/integrations/langchain/test_langchain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -752,7 +752,21 @@ def test_langchain_create_agent(
)

model_response = get_model_response(
nonstreaming_responses_model_response,
nonstreaming_responses_model_response(
message_contents=("Hello, how can I help you?",),
usage=ResponseUsage(
input_tokens=10,
input_tokens_details=InputTokensDetails(
cached_tokens=4,
cache_write_tokens=6,
),
output_tokens=20,
output_tokens_details=OutputTokensDetails(
reasoning_tokens=5,
),
total_tokens=30,
),
),
serialize_pydantic=True,
request_headers={
"X-Stainless-Raw-Response": "True",
Expand Down
18 changes: 16 additions & 2 deletions tests/integrations/litellm/test_litellm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -596,7 +596,14 @@ def test_streaming_chat_completion(

model_response = get_model_response(
server_side_event_chunks(
streaming_chat_completions_model_response,
streaming_chat_completions_model_response(
usage=CompletionUsage(
prompt_tokens=10,
completion_tokens=20,
total_tokens=30,
),
message_contents=("Tes", "t r", "esp", "ons", "e"),
),
include_event_type=False,
),
request_headers={"X-Stainless-Raw-Response": "true"},
Expand Down Expand Up @@ -713,7 +720,14 @@ async def test_async_streaming_chat_completion(
model_response = get_model_response(
async_iterator(
server_side_event_chunks(
streaming_chat_completions_model_response,
streaming_chat_completions_model_response(
usage=CompletionUsage(
prompt_tokens=10,
completion_tokens=20,
total_tokens=30,
),
message_contents=("Tes", "t r", "esp", "ons", "e"),
Comment thread
cursor[bot] marked this conversation as resolved.
),
include_event_type=False,
),
),
Expand Down
Loading
Loading